A Quick Guide to Variables and Attributes Data

March 23, 2021
3 min read

Variables data is data that is acquired through measurements. This can be length, elapsed time, diameter, strength, weight, temperature, density, thickness, pressure, or height. Accuracy can be measured, for example, to the nearest inch, centimeter, millimeter, or micron.

Attributes data is data that can be classified and counted. In attributes data, key concepts are “nonconformities” and “nonconforming.” There are two types of attributes data: counts of defects per item or group of items (nonconformities) and counts of defective items (nonconforming).

  • Nonconforming data is a count of defective units. It is often described as go/no go, pass/fail, or yes/no since there are only two possible outcomes to any given check. It is also referred to as a count of defective or rejected units. For example, a light bulb either works or, it does not. Track either the number failing or the number passing.
  • Nonconformities data is a count of defects per unit or group of units. Nonconformities can refer to defects or occurrences that should not be present but are. It also refers to any characteristic that should be present but is not. Examples of nonconformities are dents, scratches, bubbles, cracks, and missing buttons.

How are they used?

Variables data is normally analyzed in pairs of charts that present data in terms of location or central location and spread. Location, usually the top chart, shows data in relation to the process average. It is presented in X-bar, individuals, or median charts. Spread, usually the bottom chart, looks at piece-by-piece variation. Range, sigma, and moving range charts are used to illustrate process spread. Another aspect of these variables control charts is that the sample size is generally constant.

Examples: window size, closing time, tire pressure, glass thickness, daily weight gain/loss.

Attributes data is analyzed in control charts that show how a system changes over time. There are two chart options for each type of attributes data.

  • Nonconforming data is analyzed in p-charts and np-charts. Chart selection is based on the consistency of the subgroup size:
    • If the number inspected is always the same, use an np-chart.
    • If the number inspected varies with each subgroup use a p-chart.
  • Nonconformities data is analyzed in u-charts and c-charts. Chart selection is based on the consistency of the subgroup size:
    • If the number of nonconformities is counted, use a c-chart.
    • If the number inspected varies with each subgroup, use a u-chart.

Examples: errors on a math test; invoice problems (nonconformities); broken or missing parts; numbers of employees absent; broken glass products (nonconforming).